Vianney Taquet - Data & AI Manager - Forecast, Inventory Optimization & Assortment

Vianney Taquet

Data & AI Manager - Forecast, Inventory Optimization & Assortment - Value Chain

Lille, Hauts-de-France

Join Prog.AI to see contacts

Summary

🤩

Rockstar

🎓

Top School

Vianney Taquet is a Data & AI leader with 8+ years of experience translating scientific research into high-impact supply chain AI, currently leading Decathlon’s One Dispatch data efforts from Lille. He has built and scaled cross-functional teams (15+ people) and shipped a next-generation demand forecasting solution that improved accuracy by 15%, unlocking roughly €200M in annual value across Decathlon’s main supply zones. A hands-on technical contributor, he is a core developer on the scikit-learn-contrib MAPIE project for ML uncertainty estimation, reflecting strong expertise in probabilistic forecasting and risk-aware models. His background spans astrophysics and R&D at institutions like NASA, Leiden Observatory and Inria, giving him uncommon depth in large-scale scientific programming and statistical modelling. Vianney combines product-minded delivery, open-source craftsmanship, and domain expertise in time series and inventory optimization to drive measurable operational impact.

8 years of coding experience

10 years of employment as a software developer

Doctor of Philosophy (PhD), Astronomy and Astrophysics, Doctor of Philosophy (PhD), Astronomy and Astrophysics at Université Grenoble Alpes

Master 2, Astronomie et astrophysique, Master 2, Astronomie et astrophysique at Université Paris Sud (Paris XI)

Data Scientist and Machine Learning with Python Career Tracks, Data Science, Data Scientist and Machine Learning with Python Career Tracks, Data Science at DataCamp

English, French, Italian

Stackoverflow

Stats

1reputation

0reached

0answers

0questions

Github Skills (6)

scikit10

python10

classification10

scikit-learn10

data-science9

numpy8

Programming languages (2)

Jupyter NotebookPython

Github contributions (5)

scikit-learn-contrib/MAPIE

Mar 2021 - Sep 2022

A scikit-learn-compatible library for estimating prediction intervals and controlling risks, based on conformal predictions.

Role in this project:

Data Scientist

Contributions:10 releases, 1236 reviews, 124 commits in 1 year 5 months

Contributions summary:Vianney's commits focused on modifying and improving the `mapie/utils.py` and `mapie/classification.py` files. These changes primarily involved refactoring existing code, replacing the `LabelBinarizer` with `label_binarize`, removing commented lines, and adjusting probability sum checks. The user also updated the classification tutorial from the notebook and added additional examples, demonstrating involvement in model building and documentation within the project.

regressionpythonconfidence-intervalspredictiondata-science

vtaquet/momice

Aug 2018 - Jul 2020

Public version of the GRAINOBLE gas-grain astrochemical code

Contributions:77 commits, 2 PRs, 73 pushes in 1 year 10 months

gasastronomygrain

Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.

Request Free Trial